Automated 3D Neuron Tracing with Precise Branch Erasing and Confidence Controlled Back-Tracking [article]

Siqi Liu, Donghao Zhang, Yang Song, Hanchuan Peng, Weidong Cai
2017 bioRxiv   pre-print
The automatic reconstruction of single neuron cells is essential to enable large-scale data-driven investigations in computational neuroscience. However, few previous methods were able to generate satisfactory results automatically from 3D microscopic images without human intervention. We developed a new algorithm for automatic 3D neuron reconstruction. The main idea of the proposed algorithm is to iteratively track backwards from the potential neuronal termini to the soma centre. The traced
more » ... as are labelled to avoid duplicated tracing. An online confidence score is computed to decide if a tracing iteration should be stopped and discarded from the final reconstruction. The performance improvements comparing to the previous methods are mainly introduced by a more accurate estimation of the traced area and a novel confidence controlled back-tracking algorithm. The proposed algorithm supports large-scale batch-processing by requiring only a background thresh-old. We bench-tested the proposed algorithm on the datasets of the Big Neuron project. We show it outperformed several state-of-the-art methods regarding the reconstruction accuracy. It was also able to generate topologically acceptable neuronal models in a majority of cases without human intervention.
doi:10.1101/109892 fatcat:fr2kqi6ynvcezpaznlret6fcke